Skip to main content

Nvidia’s AI-powered scaling makes old games look better without a huge performance hit

Nvidia’s AI-powered scaling makes old games look better without a huge performance hit


Deep Learning Dynamic Super Resolution was added in the latest driver for RTX cards

Share this story

If you buy something from a Verge link, Vox Media may earn a commission. See our ethics statement.

Nvidia says its AI-powered upscaling is more powerful than regular super-resolution.
Nvidia says its AI-powered upscaling is more powerful than regular super-resolution.
Image: Nvidia

Nvidia’s latest game-ready driver includes a tool that could let you improve the image quality of games that your graphics card can easily run, alongside optimizations for the new God of War PC port. The tech is called Deep Learning Dynamic Super Resolution, or DLDSR, and Nvidia says you can use it to make “most games” look sharper by running them at a higher resolution than your monitor natively supports.

DLDSR builds on Nvidia’s Dynamic Super Resolution tech, which has been around for years. Essentially, regular old DSR renders a game at a higher resolution than your monitor can handle and then downscales it to your monitor’s native resolution. This leads to an image with better sharpness but usually comes with a dip in performance (you are asking your GPU to do more work, after all). So, for instance, if you had a graphics card capable of running a game at 4K but only had a 1440p monitor, you could use DSR to get a boost in clarity.

DLDSR takes DSR and adds AI

DLDSR takes the same concept and incorporates AI that can also work to enhance the image. According to Nvidia, this means you can upscale less (and therefore lose less performance) while still getting similar image quality improvements. In real numbers, Nvidia claims you’ll get image quality similar to running at four times the resolution using DSR with only 2.25 times the resolution with DLDSR. Nvidia gives an example using 2017’s Prey: Digital Deluxe running on a 1080p monitor: 4x DSR runs at 108 FPS, while 2.25x DLDSR is getting 143 FPS, only two frames per second slower than running at native 1080p.

Of course, you may want to take those impressive results with a grain of salt, as Nvidia’s obviously going to want to show one of the best-case examples. In the real world, you may get different results with different games, both in terms of FPS and what settings you have to run DLDSR in to get it looking crisp. Given its wider game support, though, you’ll probably be able to play around with it using one of your favorite older titles — though you still will need an RTX card, and they aren’t exactly easy to get right now.

Nvidia has had a lot of success with deep learning lately

This isn’t the first time Nvidia’s used deep learning to improve image quality and performance — it’s gotten a lot of praise for its Deep Learning Super Sampling, or DLSS, system. However, DLSS needs to be specifically supported by the game, and the list of games you can use it with is relatively small (though, as of today, it includes God of War).

AMD, Nvidia’s graphics card competitor, has also announced tech to improve performance and graphics on a wide array of games. It calls its approach Radeon Super Resolution, and while it doesn’t use exactly the same methods as DLSS or DLDSR (AMD has its own upscaling tech called virtual super resolution), it’s aiming towards the same goal.

If you want to try out Nvidia’s DLDSR, update to the latest driver, then open up Nvidia Control Panel app. Go to Manage 3D Settings, click the DSR - Factors drop-down, and select one of the DL Scaling options.